© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13284
    Prev
    Next
    INDEX
    Explanations

    titles related to leadership or roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.59
     ویکی‌پدی
    -0.48
    `${
    -0.43
     Gar
    -0.43
     rear
    -0.41
    بوابة
    -0.41
     Pow
    -0.40
     vVar
    -0.40
    copal
    -0.39
     незавершена
    -0.39
    POSITIVE LOGITS
     а
    0.77
    RemoveField
    0.64
     OkHttpClient
    0.52
     rumours
    0.51
    omitempty
    0.50
    caring
    0.49
    AlterField
    0.48
     быть
    0.48
     Pests
    0.48
     diría
    0.48
    Activations Density 0.107%

    No Known Activations